Cover Image

Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Jinyeong, Kang, Seil, Park, Jiwoo, Kim, Junhyeok, Hwang, Seong Jae
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding
by: Kang, Seil, et al.
Published: (2025)

See What You Are Told: Visual Attention Sink in Large Multimodal Models
by: Kang, Seil, et al.
Published: (2025)

Real-Time Visual Attribution Streaming in Thinking Model
by: Kang, Seil, et al.
Published: (2026)

Interpreting vision transformers via residual replacement model
by: Kim, Jinyeong, et al.
Published: (2025)

FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics
by: Jeong, Taejin, et al.
Published: (2026)

FALCON: Frequency Adjoint Link with CONtinuous Density Mask for Fast Single Image Dehazing
by: Kim, Donghyun, et al.
Published: (2024)

Anchoring and Rescaling Attention for Semantically Coherent Inbetweening
by: Choi, Tae Eun, et al.
Published: (2026)

Towards Continuous Sign Language Conversation from Isolated Signs
by: Kim, Youngmin, et al.
Published: (2026)

Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
by: Jun, Youngjun, et al.
Published: (2026)

Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis
by: Kim, Chanyoung, et al.
Published: (2025)

Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis
by: Han, Woojung, et al.
Published: (2025)

ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting
by: Lee, Yeonkyung, et al.
Published: (2026)

Real-Time Person Image Synthesis Using a Flow Matching Model
by: Jeong, Jiwoo, et al.
Published: (2025)

Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models
by: Hong, Sujung, et al.
Published: (2026)

CoBra: Complementary Branch Fusing Class and Semantic Knowledge for Robust Weakly Supervised Semantic Segmentation
by: Han, Woojung, et al.
Published: (2024)

Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
by: Jun, Youngjun, et al.
Published: (2024)

DragText: Rethinking Text Embedding in Point-based Image Editing
by: Choi, Gayoon, et al.
Published: (2024)

WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image
by: Park, Jiwoo, et al.
Published: (2025)

WoLF: Wide-scope Large Language Model Framework for CXR Understanding
by: Kang, Seil, et al.
Published: (2024)

Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
by: Woo, Sangmin, et al.
Published: (2024)

VLM-HOI: Vision Language Models for Interpretable Human-Object Interaction Analysis
by: Kang, Donggoo, et al.
Published: (2024)

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models
by: Lee, Dong-Jae, et al.
Published: (2026)

Mono-Modalizing Extremely Heterogeneous Multi-Modal Medical Image Registration
by: Choo, Kyobin, et al.
Published: (2025)

Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?
by: Kim, Eunki, et al.
Published: (2025)

Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
by: Kim, Jihyo, et al.
Published: (2024)

Attention Prompting on Image for Large Vision-Language Models
by: Yu, Runpeng, et al.
Published: (2024)

Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow
by: Zhang, Chengsheng, et al.
Published: (2026)

Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens
by: Kim, Sohee, et al.
Published: (2025)

How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions
by: An, Na Min, et al.
Published: (2025)

Large Language Models Facilitate Vision Reflection in Image Classification
by: An, Guoyuan, et al.
Published: (2025)

RaDL: Relation-aware Disentangled Learning for Multi-Instance Text-to-Image Generation
by: Park, Geon, et al.
Published: (2025)

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference
by: Kang, Beomseok, et al.
Published: (2026)

Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models
by: Park, Jungwon, et al.
Published: (2024)

Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection
by: Lee, Uichan, et al.
Published: (2026)

Benchmarking Direct Preference Optimization for Medical Large Vision-Language Models
by: Kim, Dain, et al.
Published: (2026)

First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models
by: Ha, Jiwoo, et al.
Published: (2026)

FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generation
by: Bill, Eric Tillmann, et al.
Published: (2026)

RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models
by: Woo, Sangmin, et al.
Published: (2024)

Objective and Interpretable Breast Cosmesis Evaluation with Attention Guided Denoising Diffusion Anomaly Detection Model
by: Park, Sangjoon, et al.
Published: (2024)

Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models
by: Hwang, Jisung, et al.
Published: (2025)